Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to informing or educating others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angle
    -0.17
    erras
    -0.17
    bbing
    -0.15
    instein
    -0.15
    aterno
    -0.15
    APA
    -0.14
    uliar
    -0.14
    onica
    -0.14
    foundland
    -0.14
    ìŀ¥ìĿĦ
    -0.14
    POSITIVE LOGITS
    ally
    0.20
    ative
    0.19
    449
    0.19
    atics
    0.16
    .nextDouble
    0.15
    aset
    0.14
     about
    0.14
    /alert
    0.14
    ¹
    0.14
    oon
    0.14
    Act Density 0.033%

    No Known Activations